AI Gateway: Rate Limit or Token Usage Limit based on specific Tag/User

Type

New feature

Description

We want to implement rate limits and token limits (usage limits) for our users. We believe it would be beneficial if the AI Gateway had this feature, as we’ve seen it in other products. This would be advantageous for us since we wouldn’t need to implement additional solutions to manage these limits.

Benefit

  • Rate Limit for each user
  • Token limit for each user
  • No another implementation needed for tracking usage or limiting usage.